论文信息 - The Brain Image Segmentation by Markov Field and Normal Distribution Curve

The Brain Image Segmentation by Markov Field and Normal Distribution Curve

Because of magnetic resonance images (MRI) was impacted of thermal/electrical noise, we found that the distribution of the brain tissue is normal distribution according to the observation and study. This paper presents a theory based on Markov Field to extract brain tissue and used fuzzy clustering theory to build a normal distribution curve on the histogram of the brain tissue image to segmentation MRI. This paper is divided into two parts: First of all, using simulated annealing based on Markov random field to obtain global energy minimization of the brain image then using threshold method extract objectives( brain bone and brain tissue ) and background; Secondly, using the histogram and fuzzy clustering method to build a normal distribution curve to achieve a better segmentation result.

[1] Donald Geman,et al. Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2] Pan Lin,et al. An efficient automatic framework for segmentation of MRI brain image , 2004, The Fourth International Conference onComputer and Information Technology, 2004. CIT '04..

[3] Donald Geman,et al. Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1984 .

[4] Koenraad Van Leemput,et al. Automated model-based tissue classification of MR images of the brain , 1999, IEEE Transactions on Medical Imaging.

[5] W. Eric L. Grimson,et al. Adaptive Segmentation of MRI Data , 1995, CVRMed.

[6] Alan C. Evans,et al. A fully automatic and robust brain MRI tissue classification method , 2003, Medical Image Anal..

[7] Suzie Vachon,et al. Le traitement des images , 2007 .

[8] G. B. Smith,et al. Preface to S. Geman and D. Geman, “Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images” , 1987 .